462 citations · 2.5k across the 127 of their papers we have counts for
30 papers · 1 filter
Benign Overfitting in Adversarially Robust Linear Classification
Jinghui Chen, Yuan Cao, Quanquan Gu
"Benign overfitting", where classifiers memorize noisy training data yet still achieve a good generalization performance, has drawn great attention in the machine learning communit…
On the Convergence and Robustness of Adversarial Training
Yisen Wang, Xingjun Ma, James Bailey +3
Improving the robustness of deep neural networks (DNNs) to adversarial examples is an important yet challenging problem for secure deep learning. Across existing defense techniques…
Iterative Teacher-Aware Learning
Luyao Yuan, Dongruo Zhou, Junhong Shen +5
In human pedagogy, teachers and students can interact adaptively to maximize communication efficiency. The teacher adjusts her teaching method for different students, and the stude…
Linear Contextual Bandits with Adversarial Corruptions
Heyang Zhao, Dongruo Zhou, Quanquan Gu
We study the linear contextual bandit problem in the presence of adversarial corruption, where the interaction between the player and a possibly infinite decision set is contaminat…
Adaptive Differentially Private Empirical Risk Minimization
Xiaoxia Wu, Lingxiao Wang, Irina Cristali +2
We propose an adaptive (stochastic) gradient perturbation method for differentially private empirical risk minimization. At each iteration, the random noise added to the gradient i…
Locally Differentially Private Reinforcement Learning for Linear Mixture Markov Decision Processes
Chonghua Liao, Jiafan He, Quanquan Gu
Reinforcement learning (RL) algorithms can be used to provide personalized services, which rely on users' private and sensitive data. To protect the users' privacy, privacy-preserv…